Skip to content

leszekgruchala/buddy / skills/change-report

change-report

Verified

Validate a PR or branch diff and create an HTML change report or walkthrough with before/after behavior, practical impact, and material architecture changes. Keep the current request in this skill; route new requests by their own scope.

FileKindSize
SKILL.mdskill md7.7 KB
assets/report.htmlother14.0 KB
references/examples.mdmarkdown1.4 KB
references/report-data.mdmarkdown8.6 KB
scripts/render_report.pyscript20.3 KB

references/examples.md

View on GitHub
# Short Outcome Examples

These illustrate wording, not verified claims. Use the actual comparison's conditions and citations; omit diagrams when they add no explanation.

| Change | Before | After | Impact |
| --- | --- | --- | --- |
| Expiry boundary fix | A session is accepted at its exact expiry time. | A session is rejected at or after expiry. | Users with an expired session must sign in again; valid sessions behave as before. |
| Search wording | The empty state says “Nothing here.” | It says “No matches. Try a shorter search.” | People with no matching results get a specific next step; search behavior is unchanged. |
| Breaking export contract | Clients read the CSV column `user_id`. | The column is named `account_id`. | Export consumers must update their column lookup before using the new CSV. |
| Documentation and tests | The interval units are undocumented and the example is untested. | The guide states seconds and a test covers the example. | Integrators can select the intended interval; runtime behavior is unchanged. |

For incomplete evidence, state the limit rather than writing a confident benefit: “The candidate accepts an optional region; the previous implementation and affected callers are unavailable, so compatibility is unverified.” Put that gap in a warning above the comparison. A description of an intended outcome does not prove that outcome works.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall